all_lm

<code>all_lm</code> estimates coefficients of a specific variable using
linear models (<code>lm</code>) with all possible combinations of other variables (potential confounding factors).

Estimates and plots effect estimates from models with all possible
combinations of a list of variables. It can be used for assessing treatment
effects in clinical trials or risk factors in bio-medical and epidemiological
research. Like Stata command 'confall' (Wang Z (2007) <doi:10.1177/1536867X0700700203> ),
'allestimates' calculates and stores all effect estimates, and plots them against p values or
Akaike information criterion (AIC) values. It currently has functions for linear
regression: all_lm(), logistic and Poisson regression: all_glm(),
and Cox proportional hazards regression: all_cox().

Zhiqiang Wang

allestimates

Effect Estimates from All Models

all_lm function

<dl><dt>crude</dt>
<dd>An object of formula for initial model, generally crude model.
However, additional variables can also be included here as the initial model.</dd>
<dt>xlist</dt>
<dd>A vector of a list of variable names (potential confounding factors).</dd>
<dt>data</dt>
<dd>Data frame.</dd>
<dt>na_omit</dt>
<dd>Remove all missing values. Default is <code>"na_omit = TRUE"</code>.</dd>
<dt>...</dt>
<dd>Further optional arguments.</dd></dl>

Arguments

Estimates all possible effect estimates using lm — all_lm

<dl>

<dt>crude</dt>
<dd>An object of formula for initial model, generally crude model.
However, additional variables can also be included here as the initial model.</dd>


<dt>xlist</dt>
<dd>A vector of a list of variable names (potential confounding factors).</dd>


<dt>data</dt>
<dd>Data frame.</dd>


<dt>na_omit</dt>
<dd>Remove all missing values. Default is <code>"na_omit = TRUE"</code>.</dd>


<dt>...</dt>
<dd>Further optional arguments.</dd>

</dl>

all_lm: Estimates all possible effect estimates using `lm`

Description

Usage

Value

Arguments

See Also

Examples